laya-decision
Use the optional local Laya decision engine for typed advisory recommendations while viStack remains authoritative for routing, execution, state, and evidence.
Skill by vianch
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vianch-laya-decision
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/laya-decision
What's inside
- Skill name
laya-decision- Description
- Use the optional local Laya decision engine for typed advisory recommendations while viStack remains authoritative for routing, execution, state, and evidence.
- License
- unknown
- Instructions
- 87 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from vianch/vistack
- 0.587score
architect
vianch
Design before implementing: ground the change, have independent runners sketch at least two structurally distinct designs (caller usage first, then types…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
html-report
vianch
Make a report, summary, status or progress page, chart, graph, diagram, flow, path or architecture view, timeline, incident or bug timeline, kanban or triage…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
interrogate
vianch
Adversarial multi-reviewer pass on a diff: independent reviewers on the current host's model get the same intent, rubric, and code-quality lens, and the lead…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
autonomy-has-fences
vianch
Run unattended everywhere except four named cases: unresolved blocker, acceptance-criteria ambiguity, irreversible action, credential problem.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
design-agent
vianch
Design and create a new agent for Claude Code, Codex, or OpenCode: ask a few preference questions, write a tight persona with one job, one voice, and explicit…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
evidence-over-inference
vianch
Cite file:line, command output, or a captured artifact for every claim; treat should/presumably/likely as unfinished work.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
figma-sync
vianch
Keep a live line to Figma while implementing a design: resolve the file key and node id for every frame, ask precisely for any missing URL, node id…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
fix-root-causes
vianch
Treat the cause rather than the symptom, and record a workaround as an explicit decision when one is unavoidable.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
make-operations-idempotent
vianch
Design lifecycle steps, commands, and monitor loops to converge after crashes, retries, and duplicate execution.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
guard-the-context-window
vianch
Treat context as the scarce resource.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
keep-origins-in-realm
vianch
Every git remote, clone, fetch, submodule, and vendored copy stays within the project organization and its approved repositories.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
advisor
vianch
Consult the advisor at the three moments that change a run's outcome — before committing to a large plan, when the same error comes back, and before calling a…
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (24 days ago)
- Last release
- Oct 6, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/vianch/vistack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from vianch
- 0.587score
interrogate
vianch
Adversarial multi-reviewer pass on a diff: independent reviewers on the current host's model get the same intent, rubric, and code-quality lens, and the lead…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
html-report
vianch
Make a report, summary, status or progress page, chart, graph, diagram, flow, path or architecture view, timeline, incident or bug timeline, kanban or triage…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
architect
vianch
Design before implementing: ground the change, have independent runners sketch at least two structurally distinct designs (caller usage first, then types…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
autonomy-has-fences
vianch
Run unattended everywhere except four named cases: unresolved blocker, acceptance-criteria ambiguity, irreversible action, credential problem.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
design-agent
vianch
Design and create a new agent for Claude Code, Codex, or OpenCode: ask a few preference questions, write a tight persona with one job, one voice, and explicit…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
evidence-over-inference
vianch
Cite file:line, command output, or a captured artifact for every claim; treat should/presumably/likely as unfinished work.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
laya-decision skill. Agent Mart. https://agentmart.dev/skills/vianch-laya-decision (last updated 2026-10-24)